This BiRefNet was trained with images in 2048x2048 for higher resolution inference. Performance: All tested in FP16 mode. Dataset Method Resolution maxFm wFmeasure MAE Smeasure meanEm HCE maxEm meanFm adpEm adpFm mBA maxBIoU meanBIoU : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : DIS VD BiRefNet HR general epoch 130 2048x2048 .925 .894 .026 .927 .952 811 .960 .909 .944 .888 .828 .837 .817 DIS VD BiRefNet HR general epoch 130 1024x1024 .876 .840 .041 .893 .913 1348 .926 .860 .930 .857 .765 .769 .742 DIS VD BiRefNet general epoch 244 2048x2048 .888 .858 .037 .898 .934 811 .941 .878 .927 .862 .802 .790 .776 DIS VD BiRefNet general epoch 244 1024x1024 .908 .877 .034 .912 .943 1128 .953 .894 .944 .881 .796 .812 .789 Bilateral Reference for High Resolution Dichotomous Image Segmentation Peng Zheng 1,4,5,6 ,  Dehong Gao 2 ,  Deng Ping Fan 1 ,  Li Liu 3 ,  Jorma Laaksonen 4 ,  Wanli Ouyang 5 ,  Nicu Sebe 6 1 Nankai University  2 Northwestern Polytechnical University  3 National University of Defense Technology  4 Aalto University  5 Shanghai AI Laboratory  6 University of Trento        &…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy